Automated quantification of baseline imaging PET metrics on FDG PET/CT images of pediatric Hodgkin lymphoma patients.
Amy J WeismanJihyun KimInki LeeKathleen M McCartenSandy KesselCindy L SchwartzKara M KellyRobert JerajSteve Y ChoTyler James BradshawPublished in: EJNMMI physics (2020)
An automated method using an ensemble of multi-resolution pathway 3D CNNs was able to quantify PET imaging features of lymphoma on baseline FDG PET/CT images with excellent agreement to reference physician PET segmentation. Automated methods with faster throughput for PET quantitation, such as MTV and TLG, show promise in more accessible clinical and research applications.
Keyphrases
- pet imaging
- deep learning
- convolutional neural network
- hodgkin lymphoma
- positron emission tomography
- pet ct
- computed tomography
- end stage renal disease
- machine learning
- newly diagnosed
- artificial intelligence
- ejection fraction
- primary care
- high throughput
- chronic kidney disease
- ms ms
- optical coherence tomography
- emergency department
- high resolution
- prognostic factors
- diffuse large b cell lymphoma
- liquid chromatography
- big data
- photodynamic therapy
- fluorescence imaging
- childhood cancer